© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14790
    Prev
    Next
    INDEX
    Explanations

    terms related to aerobics and fitness classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tracce
    -0.47
     lancar
    -0.45
    曖昧さ回避
    -0.45
     ujednoznacz
    -0.45
    jonijiet
    -0.44
    Décès
    -0.43
    Personendaten
    -0.43
    Commissioner
    -0.41
     řízení
    -0.41
     Handling
    -0.41
    POSITIVE LOGITS
     gym
    1.00
     gyms
    0.97
     fitness
    0.97
     workout
    0.91
    fitness
    0.90
     workouts
    0.87
    gym
    0.84
     Fitness
    0.83
    Fitness
    0.82
     FITNESS
    0.79
    Activations Density 0.112%

    No Known Activations